{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:49:55Z","timestamp":1780055395340,"version":"3.54.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,5,2]],"date-time":"2023-05-02T00:00:00Z","timestamp":1682985600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China Guangzhou Science and Technology Program key projects","doi-asserted-by":"publisher","award":["82230033 82271133 202103000043"],"award-info":[{"award-number":["82230033 82271133 202103000043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioeng. Biotechnol."],"abstract":"<jats:p><jats:bold>Background:<\/jats:bold> Vogt-Koyanagi-Harada (VKH) disease is a common and easily blinded uveitis entity, with choroid being the main involved site. Classification of VKH disease and its different stages is crucial because they differ in clinical manifestations and therapeutic interventions. Wide-field swept-source optical coherence tomography angiography (WSS-OCTA) provides the advantages of non-invasiveness, large-field-of-view, high resolution, and ease of measuring and calculating choroid, offering the potential feasibility of simplified VKH classification assessment based on WSS-OCTA.<\/jats:p><jats:p><jats:bold>Methods:<\/jats:bold> 15 healthy controls (HC), 13 acute-phase and 17 convalescent-phase VKH patients were included, undertaken WSS-OCTA examination with a scanning field of 15 \u00d7 9\u00a0mm<jats:sup>2<\/jats:sup>. 20 WSS-OCTA parameters were then extracted from WSS-OCTA images. To classify HC and VKH patients in acute and convalescent phases, two 2-class VKH datasets (HC and VKH) and two 3-class VKH datasets (HC, acute-phase VKH, and convalescent-phase VKH) were established by the WSS-OCTA parameters alone or in combination with best-corrected visual acuity (logMAR BCVA) and intraocular pressure (IOP), respectively. A new feature selection and classification method that combines an equilibrium optimizer and a support vector machine (called SVM-EO) was adopted to select classification-sensitive parameters among the massive datasets and to achieve outstanding classification performance. The interpretability of the VKH classification models was demonstrated based on SHapley Additive exPlanations (SHAP).<\/jats:p><jats:p><jats:bold>Results:<\/jats:bold> Based on pure WSS-OCTA parameters, we achieved classification accuracies of 91.61% \u00b1 12.17% and 86.69% \u00b1 8.30% for 2- and 3-class VKH classification tasks. By combining the WSS-OCTA parameters and logMAR BCVA, we achieved better classification performance of 98.82% \u00b1 2.63% and 96.16% \u00b1 5.88%, respectively. Through SHAP analysis, we found that logMAR BCVA and vascular perfusion density (VPD) calculated from the whole field of view region in the choriocapillaris (whole FOV CC-VPD) were the most important features for VKH classification in our models.<\/jats:p><jats:p><jats:bold>Conclusion:<\/jats:bold> We achieved excellent VKH classification performance based on a non-invasive WSS-OCTA examination, which provides the possibility for future clinical VKH classification with high sensitivity and specificity.<\/jats:p>","DOI":"10.3389\/fbioe.2023.1086347","type":"journal-article","created":{"date-parts":[[2023,5,2]],"date-time":"2023-05-02T04:35:11Z","timestamp":1683002111000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Classification of Vogt-Koyanagi-Harada disease using feature selection and classification based on wide-field swept-source optical coherence tomography angiography"],"prefix":"10.3389","volume":"11","author":[{"given":"Peng","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyuan","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gengyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyu","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuancong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongzhou","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqing","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Chi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,5,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1080\/09273948.2020.1833225","article-title":"Diagnostic value of optical coherence tomography in the early diagnosis of macular complications in chronic vogt-koyanagi-harada disease","volume":"30","author":"Agarwal","year":"2020","journal-title":"Ocul. Immunol. Inflamm."},{"key":"B2","doi-asserted-by":"publisher","first-page":"103667","DOI":"10.1016\/j.artint.2022.103667","article-title":"Relation between prognostics predictor evaluation metrics and local interpretability SHAP values","volume":"306","author":"Baptista","year":"2022","journal-title":"Artif. Intell."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1765","DOI":"10.1109\/JBHI.2018.2865218","article-title":"IMU-based classification of Parkinson\u2019s disease from gait: A sensitivity analysis on sensor location and feature selection","volume":"22","author":"Caramia","year":"2018","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B4","doi-asserted-by":"publisher","first-page":"637489","DOI":"10.3389\/fcell.2021.637489","article-title":"Identification of urine metabolic biomarkers for vogt-koyanagi-harada disease","volume":"9","author":"Chang","year":"2021","journal-title":"Front. Cell Dev. Biol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"528","DOI":"10.3109\/09273948.2016.1151896","article-title":"Comparison of enhanced depth imaging and swept source optical coherence tomography in assessment of choroidal thickness in vogt\u2013koyanagi\u2013harada disease","volume":"25","author":"Chee","year":"2017","journal-title":"Ocul. Immunol. Inflamm."},{"key":"B6","doi-asserted-by":"publisher","first-page":"108070","DOI":"10.1016\/j.exer.2020.108070","article-title":"Plasma metabolomics study of Vogt-Koyanagi-Harada disease identifies potential diagnostic biomarkers","volume":"196","author":"Chen","year":"2020","journal-title":"Exp. Eye Res."},{"key":"B7","doi-asserted-by":"publisher","first-page":"3862","DOI":"10.1109\/TII.2019.2940475","article-title":"Linear priors mined and integrated for transparency of blast furnace black-box SVM model","volume":"16","author":"Chen","year":"2020","journal-title":"IEEE Trans. Ind. Inf."},{"key":"B8","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.ajo.2020.07.036","article-title":"Vogt-koyanagi-harada disease managed with immunomodulatory therapy within 3 Months of disease onset","volume":"220","author":"EiOo","year":"2020","journal-title":"Am. J. Ophthalmol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1038\/s41433-020-01210-5","article-title":"Evaluation of microvasculature alterations in convalescent Vogt-Koyanagi-Harada disease using optical coherence tomography angiography","volume":"35","author":"Fan","year":"2021","journal-title":"Eye"},{"key":"B10","doi-asserted-by":"publisher","first-page":"105190","DOI":"10.1016\/j.knosys.2019.105190","article-title":"Equilibrium optimizer: A novel optimization algorithm","volume":"191","author":"Faramarzi","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.joco.2018.10.011","article-title":"Revised diagnostic criteria\u201d for Vogt-Koyanagi-Harada disease fail to improve disease management","volume":"31","author":"Hedayatfar","year":"2019","journal-title":"J. Curr. Ophthalmol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s40662-021-00244-4","article-title":"Development of a classification system based on corneal biomechanical properties using artificial intelligence predicting keratoconus severity","volume":"8","author":"Herber","year":"2021","journal-title":"Eye Vis."},{"key":"B13","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1038\/s41433-021-01573-3","article-title":"Precise, simplified diagnostic criteria and optimised management of initial-onset vogt\u2013koyanagi\u2013harada disease: An updated review","volume":"36","author":"Herbort","year":"2021","journal-title":"Eye"},{"key":"B14","doi-asserted-by":"publisher","first-page":"3165","DOI":"10.1007\/s00521-021-06580-9","article-title":"An efficient equilibrium optimizer with support vector regression for stock market prediction","volume":"34","author":"Houssein","year":"","journal-title":"Neural comput. Appl."},{"key":"B15","doi-asserted-by":"publisher","first-page":"115131","DOI":"10.1016\/j.eswa.2021.115131","article-title":"An efficient ECG arrhythmia classification method based on Manta ray foraging optimization","volume":"181","author":"Houssein","year":"","journal-title":"Expert Syst. Appl."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s00417-020-04676-x","article-title":"Assessment of macular capillary perfusion in patients with inactive vogt-koyanagi-harada disease: An optical coherence tomography angiography study","volume":"258","author":"Karaca","year":"2020","journal-title":"Graefes Arch. Clin. Exp. Ophthalmol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1378","DOI":"10.1016\/j.gendis.2021.06.002","article-title":"Identification of differently expressed mRNAs by peripheral blood mononuclear cells in Vogt-Koyanagi-Harada disease","volume":"9","author":"Li","year":"2021","journal-title":"Genes Dis."},{"key":"B18","doi-asserted-by":"publisher","first-page":"3395","DOI":"10.1007\/s00417-021-05238-5","article-title":"Decrease of choriocapillary vascular density measured by optical coherence tomography angiography in Vogt-Koyanagi-Harada disease","volume":"259","author":"Liang","year":"2021","journal-title":"Graefes Arch. Clin. Exp. Ophthalmol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1080\/09273948.2020.1751212","article-title":"Retinal microcirculation defects on OCTA correlate with active inflammation and vision in vogt\u2013koyanagi\u2013harada disease","volume":"29","author":"Liang","year":"2020","journal-title":"Ocul. Immunol. Inflamm."},{"key":"B20","doi-asserted-by":"publisher","first-page":"102621","DOI":"10.1016\/j.ebiom.2019.102621","article-title":"A practical model for the identification of congenital cataracts using machine learning","volume":"51","author":"Lin","year":"2020","journal-title":"EBioMedicine"},{"key":"B21","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"B22","unstructured":"A unified approach to interpreting model predictions10\n            LundbergS. M.\n            LeeS.-I.\n          2017"},{"key":"B23","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery","volume":"2","author":"Lundberg","year":"2018","journal-title":"Nat. Biomed. Eng."},{"key":"B24","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1080\/09273948.2019.1695856","article-title":"Distinguishing microvasculature features of vogt-koyanagi-harada in patients in acute and convalescent phases using optical coherence tomography angiography","volume":"29","author":"Luo","year":"2021","journal-title":"Ocul. Immunol. Inflamm."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1250","DOI":"10.3389\/fnins.2019.01250","article-title":"sEMG-based trunk compensation detection in rehabilitation training","volume":"13","author":"Ma","year":"2019","journal-title":"Front. Neurosci."},{"key":"B26","doi-asserted-by":"publisher","first-page":"106584","DOI":"10.1016\/j.cmpb.2021.106584","article-title":"Explanation of machine learning models using shapley additive explanation and application for real data in hospital","volume":"214","author":"Nohara","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.survophthal.2016.05.002","article-title":"Vogt-Koyanagi-Harada disease","volume":"62","author":"O\u2019Keefe","year":"2017","journal-title":"Surv. Ophthalmol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"123676","DOI":"10.1016\/j.energy.2022.123676","article-title":"Interpretable machine-learning model with a collaborative game approach to predict yields and higher heating value of torrefied biomass","volume":"249","author":"Onsree","year":"2022","journal-title":"Energy"},{"key":"B29","doi-asserted-by":"publisher","first-page":"115882","DOI":"10.1016\/j.eswa.2021.115882","article-title":"Efficient high-dimension feature selection based on enhanced equilibrium optimizer","volume":"187","author":"Ouadfel","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"B30","doi-asserted-by":"publisher","first-page":"698644","DOI":"10.3389\/fmed.2021.698644","article-title":"Widefield swept-source optical coherence tomography angiography assessment of choroidal changes in vogt-koyanagi-harada disease","volume":"8","author":"Qian","year":"2021","journal-title":"Front. Med."},{"key":"B31","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1016\/s0002-9394(01)00925-4","article-title":"Revised diagnostic criteria for vogt-koyanagi-harada disease: Report of an international committee on nomenclature","volume":"131","author":"Read","year":"2001","journal-title":"Am. J. Ophthalmol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"4146","DOI":"10.1016\/j.eswa.2013.01.032","article-title":"Feature selection for medical diagnosis: Evaluation for cardiovascular diseases","volume":"40","author":"Shilaskar","year":"2013","journal-title":"Expert Syst. Appl."},{"key":"B33","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/S0002-9394(14)75078-0","article-title":"Vogt\u2013koyanagi\u2013harada syndrome","volume":"90","author":"Snyder","year":"1980","journal-title":"Am. J. Ophthalmol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.ajo.2016.07.023","article-title":"Choriocapillaris flow features follow a power law distribution: Implications for characterization and mechanisms of disease progression","volume":"170","author":"Spaide","year":"2016","journal-title":"Am. J. Ophthalmol."},{"key":"B35","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1016\/j.ajo.2021.03.036","article-title":"Classification criteria for vogt-koyanagi-harada disease","volume":"228","author":"Standardization of Uveitis Nomenclature (Sun) Working Group","year":"","journal-title":"Am. J. Ophthalmol."},{"key":"B36","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.ajo.2021.03.061","article-title":"Development of classification criteria for the uveitides","volume":"228","author":"Standardization of Uveitis Nomenclature (Sun) Working Group","year":"","journal-title":"Am. J. Ophthalmol."},{"key":"B37","first-page":"9","article-title":"Vogt-Koyanagi-Harada disease","volume":"22","author":"Sugiura","year":"1978","journal-title":"Jpn. J. Ophthalmol."},{"key":"B38","doi-asserted-by":"publisher","first-page":"110180","DOI":"10.1016\/j.measurement.2021.110180","article-title":"Bearing fault identification based on stacking modified composite multiscale dispersion entropy and optimised support vector machine","volume":"186","author":"Tan","year":"2021","journal-title":"Measurement"},{"key":"B39","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1186\/s40662-020-00214-2","article-title":"A machine learning-based algorithm used to estimate the physiological elongation of ocular axial length in myopic children","volume":"7","author":"Tang","year":"2020","journal-title":"Eye Vis."},{"key":"B40","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1136\/bjophthalmol-2019-315651","article-title":"Artificial intelligence for anterior segment diseases: Emerging applications in ophthalmology","volume":"105","author":"Ting","year":"2021","journal-title":"Br. J. Ophthalmol."},{"key":"B41","doi-asserted-by":"publisher","first-page":"5713","DOI":"10.1167\/iovs.17-22865","article-title":"Optical coherence tomography angiography macular and peripapillary vessel perfusion density in healthy subjects, glaucoma suspects, and glaucoma patients","volume":"58","author":"Triolo","year":"2017","journal-title":"Investig. Opthalmology Vis. Sci."},{"key":"B42","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1016\/j.ophtha.2017.02.006","article-title":"Impact of multiple en face image averaging on quantitative assessment from optical coherence tomography angiography images","volume":"124","author":"Uji","year":"2017","journal-title":"Ophthalmology"},{"key":"B43","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/s12348-020-00214-2","article-title":"Initial-onset acute and chronic recurrent stages are two distinctive courses of Vogt-Koyanagi-Harada disease","volume":"10","author":"Urzua","year":"2020","journal-title":"J. Ophthalmic Inflamm. Infect."},{"key":"B44","doi-asserted-by":"publisher","first-page":"104813","DOI":"10.1016\/j.compbiomed.2021.104813","article-title":"Interpretable prediction of 3-year all-cause mortality in patients with heart failure caused by coronary heart disease based on machine learning and SHAP","volume":"137","author":"Wang","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"B45","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1001\/jamaophthalmol.2018.2664","article-title":"Development and evaluation of diagnostic criteria for vogt-koyanagi-harada disease","volume":"136","author":"Yang","year":"2018","journal-title":"JAMA Ophthalmol."},{"key":"B46","doi-asserted-by":"publisher","first-page":"719593","DOI":"10.3389\/fmed.2021.719593","article-title":"Microvasculature features of vogt-koyanagi-harada disease revealed by widefield swept-source optical coherence tomography angiography","volume":"8","author":"Ye","year":"2021","journal-title":"Front. Med."}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2023.1086347\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,2]],"date-time":"2023-05-02T04:35:16Z","timestamp":1683002116000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2023.1086347\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,2]]},"references-count":46,"alternative-id":["10.3389\/fbioe.2023.1086347"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2023.1086347","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,2]]},"article-number":"1086347"}}